🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the FuriosaAI RNGD run CodeT5-large?
Yes — here's how fast and up to what context, with real measured numbers.
CodeT5-large on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 627k | 633.1-769.5 t/s | ~16.9-20.5 (slow) |
| Q8 | yes | 639k | 1266.2-1539 t/s | ~33.8-41 (slow) |
| Q4 | yes | 644k | 2261.1-2748.1 t/s | ~60.3-73.3 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
FAQ
Can the FuriosaAI RNGD run CodeT5-large?▶
Yes. At Q4 it generates ~2261.1-2748.1 tok/s and fits up to 644k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~60.3-73.3 tok/s.
How much context fits?▶
At Q4, up to about 644k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.